R Notebook

Loading the Packages

library(pacman)

Paket 㤼㸱pacman㤼㸲 wurde unter R Version 3.4.3 erstellt

p_load(tidyverse, haven,sjmisc,
                     forcats, weights, car,
                     countrycode, lavaan,
                     semTools, lavaan.survey,
                     survey, reshape2, favstats,
                     magrittr)

Installing package into 㤼㸱C:/Users/Fabio/Documents/R/win-library/3.4㤼㸲
(as 㤼㸱lib㤼㸲 is unspecified)
cannot open URL 'http://www.stats.ox.ac.uk/pub/RWin/src/contrib/PACKAGES.rds': HTTP status was '404 Not Found'also installing the dependency 㤼㸱gdata㤼㸲

cannot open URL 'http://www.stats.ox.ac.uk/pub/RWin/bin/windows/contrib/3.4/PACKAGES.rds': HTTP status was '404 Not Found'trying URL 'https://cran.rstudio.com/bin/windows/contrib/3.4/gdata_2.18.0.zip'
Content type 'application/zip' length 1186415 bytes (1.1 MB)
downloaded 1.1 MB

trying URL 'https://cran.rstudio.com/bin/windows/contrib/3.4/weights_0.85.zip'
Content type 'application/zip' length 94358 bytes (92 KB)
downloaded 92 KB

package ‘weights’ successfully unpacked and MD5 sums checked

The downloaded binary packages are in
    C:\Users\Fabio\AppData\Local\Temp\RtmpEjCCs5\downloaded_packages

weights installed
package 㤼㸱weights㤼㸲 was built under R version 3.4.3package 㤼㸱Hmisc㤼㸲 was built under R version 3.4.3package 㤼㸱mice㤼㸲 was built under R version 3.4.3Installing package into 㤼㸱C:/Users/Fabio/Documents/R/win-library/3.4㤼㸲
(as 㤼㸱lib㤼㸲 is unspecified)
trying URL 'https://cran.rstudio.com/bin/windows/contrib/3.4/countrycode_0.19.zip'
Content type 'application/zip' length 50059 bytes (48 KB)
downloaded 48 KB

package ‘countrycode’ successfully unpacked and MD5 sums checked

countrycode installed
package 㤼㸱countrycode㤼㸲 was built under R version 3.4.3Installing package into 㤼㸱C:/Users/Fabio/Documents/R/win-library/3.4㤼㸲
(as 㤼㸱lib㤼㸲 is unspecified)
also installing the dependency 㤼㸱pbivnorm㤼㸲

trying URL 'https://cran.rstudio.com/bin/windows/contrib/3.4/pbivnorm_0.6.0.zip'
Content type 'application/zip' length 38777 bytes (37 KB)
downloaded 37 KB

trying URL 'https://cran.rstudio.com/bin/windows/contrib/3.4/lavaan_0.5-23.1097.zip'
Content type 'application/zip' length 875541 bytes (855 KB)
downloaded 855 KB

package ‘pbivnorm’ successfully unpacked and MD5 sums checked

The downloaded binary packages are in
    C:\Users\Fabio\AppData\Local\Temp\RtmpEjCCs5\downloaded_packages

lavaan installed
package 㤼㸱lavaan㤼㸲 was built under R version 3.4.3Installing package into 㤼㸱C:/Users/Fabio/Documents/R/win-library/3.4㤼㸲
(as 㤼㸱lib㤼㸲 is unspecified)
trying URL 'https://cran.rstudio.com/bin/windows/contrib/3.4/semTools_0.4-14.zip'
downloaded 1.5 MB

package ‘semTools’ successfully unpacked and MD5 sums checked

The downloaded binary packages are in
    C:\Users\Fabio\AppData\Local\Temp\RtmpEjCCs5\downloaded_packages

semTools installed
package 㤼㸱semTools㤼㸲 was built under R version 3.4.3Installing package into 㤼㸱C:/Users/Fabio/Documents/R/win-library/3.4㤼㸲
(as 㤼㸱lib㤼㸲 is unspecified)
trying URL 'https://cran.rstudio.com/bin/windows/contrib/3.4/lavaan.survey_1.1.3.1.zip'
downloaded 373 KB

The downloaded binary packages are in
    C:\Users\Fabio\AppData\Local\Temp\RtmpEjCCs5\downloaded_packages

lavaan.survey installed
package 㤼㸱lavaan.survey㤼㸲 was built under R version 3.4.3package 㤼㸱survey㤼㸲 was built under R version 3.4.3package 㤼㸱favstats㤼㸲 is not available (for R version 3.4.2)Bioconductor version 3.6 (BiocInstaller 1.28.0), ?biocLite for help
there is no package called 㤼㸱favstats㤼㸲

Loading the URLs

afro5_url <- url("https://github.com/favstats/database_delib/raw//master/afro5.RData")
afro6_url <- url("https://github.com/favstats/database_delib/raw//master/afro6.RData")
latino2013_url <- url("https://github.com/favstats/database_delib/raw//master/latino2013.RData")
latino2015_url <- url("https://github.com/favstats/database_delib/raw//master/latino2015.RData")
wvs_raw_url <- url("https://github.com/favstats/database_delib/raw//master/wvs_raw.RData")
americas_url <- url("https://github.com/favstats/database_delib/raw//master/americas.RData")
bolivia_url <- url("https://github.com/favstats/database_delib/raw//master/bolivia.RData")
canada_url <- url("https://github.com/favstats/database_delib/raw//master/canada.RData")
asian_raw_url <- url("https://github.com/favstats/database_delib/raw//master/asian_raw.RData")
myanmar_raw_url <- url("https://github.com/favstats/database_delib/raw//master/myanmar_raw.RData")
mongolia_raw_url <- url("https://github.com/favstats/database_delib/raw//master/mongolia_raw.RData")
philip_raw_url <- url("https://github.com/favstats/database_delib/raw//master/philip_raw.RData")
taiwan_raw_url <- url("https://github.com/favstats/database_delib/raw//master/taiwan_raw.RData")
thai_raw_url <- url("https://github.com/favstats/database_delib/raw//master/thai_raw.RData")
malay_raw_url <- url("https://github.com/favstats/database_delib/raw//master/malay_raw.RData")
singapore_raw_url <- url("https://github.com/favstats/database_delib/raw//master/singapore_raw.RData")
sk_raw_url <- url("https://github.com/favstats/database_delib/raw//master/sk_raw.RData")
cambodia_raw_url <- url("https://github.com/favstats/database_delib/raw//master/cambodia_raw.RData")
ESS_raw_url <- url("https://github.com/favstats/database_delib/blob/master/ESS_raw.Rdata?raw=true")
vdems_start_url <- url("https://github.com/favstats/database_delib/raw//master/vdems_start.Rdata")
qog_url <- url("https://github.com/favstats/database_delib/raw//master/qog.Rdata")

Afrobarometer Data

Afro 5

load(afro5_url)
delete_na_afro <- function(x) {
  x <- Recode(x, "9 = NA;
    trust_gov = Q59A,
    trust_parliament = Q59B,
    trust_police = Q59H,
  mutate(
    sex = sex - 1, # sex (0/1) codieren
      999 = NA"
    ),
    cntry = to_label(COUNTRY_ALPHA),
    year = as.numeric(format(DATEINTR, "%Y"))
  ) %>%
  select(
    cntry, year, age, sex, income, educ, work, demtoday, trust_gov, trust_parliament,
    trust_police, trust_courts
  ) %>%
  mutate_at(
    vars(
      income, demtoday, educ,
      trust_gov, trust_parliament,
      trust_police, trust_courts
    ),
    range01
  )

package 㤼㸱bindrcpp㤼㸲 was built under R version 3.4.3Error in inherits(x, "fun_list") : object 'range01' not found

Afro 6

load(afro6_url)
afro_6 <- afro6 %>%
  rename(
    educ = Q97,
    sex = Q101,
    work = Q95,
    trust_gov = Q52A,
    trust_parliament = Q52B,
    trust_police = Q52H,
    trust_courts = Q52J,
    demtoday = Q40
  ) %>% # NAs deleten
  mutate(
    age = Recode(
      Q1, # missing values l?schen
    demtoday = Recode(
      demtoday,
      "8 = NA"
    ),
    cntry = to_label(COUNTRY_R5List),
  #                 trust_police, trust_courts),
  #            as.character) %>%
  #  mutate_at(vars(income, demtoday, educ, age,
afro_6

Merging the Data

afro_real <- afro_5 %>% select(
  cntry, year, educ, income, 
  sex, age, work, demtoday, 
  trust_gov, trust_parliament,
  trust_police, trust_courts
)
afro_real2 <- afro_6 %>% select(
  cntry, year, educ, income, 
  sex, age, work, demtoday, 
  trust_gov, trust_parliament,
  trust_police, trust_courts
)
# length(unique(afro_real$cntry))
# length(unique(afro_real2$cntry))
# table(afro_real2$year)
afro <- rbind(afro_real, afro_real2) %>% as.tbl()
afro

Latino Barometro

Latino 2013

load(latino2013_url)
latino_2013 <- latino2013 %>%
  rename(
    educ = REEDUC_1,
    income = S6,
    demtoday = P50TGB.A,
    age = S11
  ) %>%
  mutate(
    sex = S10 - 1, # sex variable erstellen
    cntry = to_label(IDENPA), # cntry variable erstellen
    trust_gov = 5 - P26TGB.B,
    trust_parliament = 5 - P26TGB.C,
    )
  ) %>%
  select(
    cntry, year, age, sex, income, educ, work, demtoday, trust_gov, trust_parliament,
    trust_police, trust_courts
  ) %>%
  #  mutate_at(vars(income, demtoday, educ,
  #                 trust_gov, trust_parliament,
  #                 trust_police, trust_courts),
  #            as.character) %>%
  #  mutate_at(vars(income, demtoday, educ,
  #                 trust_gov, trust_parliament,
  #                 trust_police, trust_courts),
  #            as.numeric) %>%
  mutate_at(
    vars(
      income, demtoday, educ,
      trust_gov, trust_parliament,
      trust_police, trust_courts
    ),
    range01
  )
latino_2013

Latino 2015

load(latino2015_url)
latino_2015 <- latino2015 %>%
  mutate(sex = S12 - 1) %>% # sex variable erstellen
  rename(
    educ = REEDUC_1,
    income = S4,
    demtoday = P17STGBS,
    age = S13
  ) %>%
  mutate(
    trust_gov = 5 - P16ST.G,
    trust_parliament = 5 - P16ST.F,
    trust_police = 5 - P16TGB.B,
    trust_courts = 5 - P16ST.H,
    work = Recode(
      S21.A,
      "2 = 1;
       3 = 1;
       4 = 0;
       5 = 0;
       6 = 0;
       7 = 0"
    ),
    cntry = to_label(IDENPA),
    income = 5 - income,
  #                 trust_gov, trust_parliament,
  #                 trust_police, trust_courts),
  #                                as.numeric) %>%
  mutate_at(
    vars(
      income, demtoday, educ,
      trust_gov, trust_parliament,
      trust_police, trust_courts
    ),
    range01
  )
latino_2015

Merging the Data

latino_real <- latino_2013 %>% select(
  cntry, year, educ, income, 
  sex, age, work, demtoday, 
  trust_gov, trust_parliament,
  trust_police, trust_courts
)
latino_real2 <- latino_2015 %>% select(
  cntry, year, educ, income, 
  sex, age, work, demtoday, 
  trust_gov, trust_parliament,
  trust_police, trust_courts
)
latino <- rbind(latino_real, latino_real2) %>% as.tbl()
latino

World Value Survey

load(wvs_raw_url)
wvs <- wvs_raw %>%
  rename(
    educ = V248,
    trust_police = 5 - V113,
    trust_courts = 5 - V114,
    work = Recode(
      V229,
      "2 = 1;
       3 = 1;
       4 = 0;
       5 = 0;
       6 = 0;
       7 = 0;
       8 = 0"
    ),
    cntry = to_label(V2)
  ) %>%
  select(
    cntry, year, age, sex, income, educ, work, demtoday,
    trust_gov, trust_parliament,
    trust_police, trust_courts
  ) %>%
  mutate_at(
    vars(
      income, demtoday, educ,
      trust_gov, trust_parliament,
      trust_police, trust_courts
    ),
    as.character
  ) %>%
  mutate_at(
    vars(
      income, demtoday, educ,
      trust_gov, trust_parliament,
      trust_police, trust_courts
    ),
    as.numeric
  ) %>%
  mutate_at(
    vars(
      income, demtoday, educ,
      trust_gov, trust_parliament,
      trust_police, trust_courts
    ),
    range01
  )
wvs

Americas Barometer

Americas Main

load(americas_url)
americas_ <- americas %>%
  mutate(cntry = to_label(pais)) %>%
  select(
    cntry, ocup4a, ed, q10new, q1, q2,
    b10a, b13, b18, b21a, n3, year
  ) %>%
  rename(
    work = ocup4a,
    educ = ed,
    income = q10new,
    sex = q1,
    age = q2,
    trust_courts = b10a,
    trust_parliament = b13,
    trust_police = b18,
    trust_gov = b21a,
    demtoday = n3
  ) %>%
  mutate(
    sex = sex - 1, # sex variable erstellen
    work = Recode(
      work,
      "2 = 1;
       3 = 1;
       4 = 0;
       5 = 0;
       6 = 0;
       7 = 0"
    )
  ) %>%
  mutate_at(
    vars(
      income, demtoday, educ,
      trust_gov, trust_parliament,
      trust_police, trust_courts
    ),
    range01
  )
americas_

Bolivia

load(bolivia_url)
bolivia_ <- bolivia %>%
  mutate(cntry = to_label(pais)) %>%
  select(
    cntry, ocup4a, ed, q10new, q1, q2,
    b10a, b13, b18, b21a, n3, year
  ) %>%
  rename(
    work = ocup4a,
    educ = ed,
    income = q10new,
    sex = q1,
    age = q2,
    trust_courts = b10a,
    trust_parliament = b13,
    trust_police = b18,
    trust_gov = b21a, # viele missing values
    demtoday = n3
  ) %>%
  mutate(
    sex = sex - 1, # sex variable erstellen
    work = Recode(
      work,
      "2 = 1;
       3 = 1;
       4 = 0;
       5 = 0;
       6 = 0;
       7 = 0"
    )
  ) %>%
  mutate_at(
    vars(
      income, demtoday, educ,
      trust_gov, trust_parliament,
      trust_police, trust_courts
    ),
    range01
  )

Canada

load(canada_url)
canada_ <- canada %>%
  mutate(cntry = to_label(pais)) %>%
  select(
    cntry, exc13, education, q10, q1, q2,
    b10a, b13, b18, b21a, n3, year
  ) %>%
  rename(
    work = exc13,
    educ = education,
    income = q10,
    sex = q1,
    age = q2,
    trust_courts = b10a,
    trust_parliament = b13,
    trust_police = b18,
    trust_gov = b21a,
    demtoday = n3
  ) %>%
  mutate(
    sex = sex - 1, # sex variable erstellen
    work = work - 1,
    income = ifelse(income == 88, NA, income)
  ) %>%
  mutate_at(
    vars(
      income, demtoday, educ,
      trust_gov, trust_parliament,
      trust_police, trust_courts
    ),
    range01
  )

Merging the Data

americas <- americas_ %>% dplyr::select(
  cntry, year, educ, income, 
  sex, age, work, demtoday, 
  trust_gov, trust_parliament,
  trust_police, trust_courts
)
bolivia <- bolivia_ %>% dplyr::select(
  cntry, year, educ, income, 
  sex, age, work, demtoday, 
  trust_gov, trust_parliament,
  trust_police, trust_courts
)
canada <- canada_ %>% dplyr::select(
  cntry, year, educ, income, 
  sex, age, work, demtoday, 
  trust_gov, trust_parliament,
  trust_police, trust_courts
)
americas <- rbind(americas, bolivia, canada)
americas

Asian Barometer

load(asian_raw_url)
delete_na_asian <- function(x) {
  x <- Recode(
    x,
    "-2 = NA;
      7 = NA;
      8 = NA;
      9 = NA;
     97 = NA;
     98 = NA;
     99 = NA;
     -1 = NA"
  )
  return(x)
} # Funktion um die NAs im asian Datensatz zu bestimmen
asian_3 <- asian_raw %>%
  rename(
    educ = se5,
    trust_gov = q9,
    trust_parliament = q11,
    trust_police = q14,
    trust_courts = q8,
    sex = se2,
    income = se13a,
    work = se9
  ) %>%
  mutate_at(
    vars(
      income, trust_gov, trust_parliament,
      trust_police, trust_courts, work, sex
    ),
    delete_na_asian
  ) %>% # NAs deleten
  mutate(
    trust_gov = 5 - trust_gov,
    trust_parliament = 5 - trust_parliament,
    trust_police = 5 - trust_police,
    trust_courts = 5 - trust_courts,
    sex = sex - 1, # sex (0/1) codieren
    income = Recode(
      income,
      "0 = NA"
    ),
    income = 5 - income,
    work = Recode(
      work, # work (0/1) codieren
      "2 = 0"
    ),
    age = Recode(
      se3a, # missing values l?schen
      "-1 = NA"
    ),
    demtoday = Recode(
      q91,
      "-1 = NA;
       97 = NA;
       98 = NA;
       99 = NA"
    ),
    educ = Recode(
      educ,
      "-1 = NA;
       98 = NA;
       99 = NA"
    ),
    cntry = to_label(country),
    year = as.numeric(format(ir9, "%Y"))
  ) %>%
  select(
    cntry, year, age, sex, income, educ, work, demtoday, trust_gov, trust_parliament,
    trust_police, trust_courts
  ) %>%
  #  mutate_at(vars(income, demtoday, educ, age,
  #                 trust_gov, trust_parliament,
  #                 trust_police, trust_courts),
  #            as.character) %>%
  #  mutate_at(vars(income, demtoday, educ, age,
  #                 trust_gov, trust_parliament,
  #                 trust_police, trust_courts),
  #            as.numeric) %>%
  mutate_at(
    vars(
      income, demtoday, educ,
      trust_gov, trust_parliament,
      trust_police, trust_courts
    ),
    range01
  )
asian_3

Wave 4

load(myanmar_raw_url)
needed <- function(data) {
  ss <- data %>%
    rename(
      educ = se5,
      trust_gov = q9,
      trust_parliament = q11,
      trust_police = q14,
      trust_courts = q8,
      sex = se2,
      income = se13a,
      work = se9
    ) %>%
    mutate_at(
      vars(
        income, trust_gov, trust_parliament,
        trust_police, trust_courts, work, sex
      ),
      delete_na_asian
    ) %>% # NAs deleten
    mutate(
      trust_gov = 5 - trust_gov,
      trust_parliament = 5 - trust_parliament,
      trust_police = 5 - trust_police,
      trust_courts = 5 - trust_courts,
      sex = sex - 1, # sex (0/1) codieren
      income = Recode(
        income,
        "0 = NA"
      ),
      work = Recode(
        work, # work (0/1) codieren
        "2 = 0"
      ),
      age = Recode(
        se3_2, # missing values l?schen
        "-1 = NA"
      ),
      demtoday = Recode(
        q94,
        "-1 = NA;
         97 = NA;
         98 = NA;
         99 = NA"
      ),
      educ = Recode(
        educ,
        "-1 = NA;
         98 = NA;
         99 = NA"
      ),
      cntry = to_label(country),
      year = year
    ) %>%
    select(
      cntry, year, age, sex, income, educ, work, demtoday, 
      trust_gov, trust_parliament, trust_police, trust_courts
    ) %>%
    #   mutate_at(vars(income, demtoday, educ, age,
    #                  trust_gov, trust_parliament,
    #                  trust_police, trust_courts),
    #             as.character) %>%
    #   mutate_at(vars(income, demtoday, educ, age,
    #                  trust_gov, trust_parliament,
    #                  trust_police, trust_courts),
    #             as.numeric) %>%
    mutate_at(
      vars(
        income, demtoday, educ,
        trust_gov, trust_parliament,
        trust_police, trust_courts
      ),
      range01
    )
  return(ss)
}
myanmar <- needed(myanmar_raw)
load(philip_raw_url)
load(taiwan_raw_url)
load(thai_raw_url)
load(malay_raw_url)
load(singapore_raw_url)
load(sk_raw_url)
load(cambodia_raw_url)
philip <- needed(philip_raw)
taiwan <- needed(taiwan_raw)

no non-missing arguments to max; returning -Infno non-missing arguments to min; returning Inf

thai <- needed(thai_raw)
malay <- needed(malay_raw)
singapore <- needed(singapore_raw) # Singapore hat extrem viele Missing values
sk <- needed(sk_raw)
cambodia <- needed(cambodia_raw)
asian <- rbind(
  asian_3, myanmar, cambodia, sk, singapore, malay, thai, taiwan, philip,
  cambodia, mongolia

European Social Survey

load(ESS_raw_url)
ESS <- ESS_raw %>%
  rename(
    demtoday = dmcntov,
      eisced,
      "55 = NA"
    ),
    work = ifelse(mnactic == 1, 1, 0),
    sex = gndr - 1, # sex variable erstellen
    cntry = to_label(cntry)
  ) %>%
  #                 trust_police, trust_courts),
  #            as.numeric) %>%
  mutate_at(
    vars(
      income, demtoday, educ,
      trust_gov, trust_parliament,
      trust_police, trust_courts
    ),
    stdz
  ) %>%
  mutate_at(
    vars(
      income, demtoday, educ,
      trust_gov, trust_parliament,
      trust_police, trust_courts
    ),
    range01
  )
ESS

Merging Everything

afro %<>% 
  mutate(survey = rep("afro", nrow(afro))) %>% 
  mutate(cntry = countrycode(cntry, "country.name.en", "country.name.en"))
latino %<>%  
  mutate(survey = rep("latino", nrow(latino))) %>% 
  mutate(cntry = countrycode(cntry, "country.name.en", "country.name.en"))
americas %<>%  
  mutate(survey = rep("americas", nrow(americas))) %>% 
  mutate(cntry = countrycode(cntry, "country.name.en", "country.name.en"))

Some values were not matched unambiguously: Hait攼㹤

wvs %<>%  
  mutate(survey = rep("wvs", nrow(wvs))) %>% 
  mutate(cntry = countrycode(cntry, "country.name.en", "country.name.en"))
ESS %<>%  
  mutate(survey = rep("ESS", nrow(ESS))) %>% 
unique(ESS$cntry)

 [1] "Albania"                                              "Belgium"                                             
 [3] "Bulgaria"                                             "Switzerland"                                         
 [5] "Cyprus"                                               "Czech Republic"                                      
 [7] "Germany"                                              "Denmark"                                             
 [9] "Estonia"                                              "Spain"                                               
[11] "Finland"                                              "France"                                              
[13] "United Kingdom of Great Britain and Northern Ireland" "Hungary"                                             
[15] "Ireland"                                              "Israel"                                              
[17] "Iceland"                                              "Italy"                                               
[19] "Lithuania"                                            "Netherlands"                                         
[21] "Norway"                                               "Poland"                                              
[23] "Portugal"                                             "Russian Federation"                                  
[25] "Sweden"                                               "Slovenia"                                            
[27] "Slovakia"                                             "Ukraine"                                             
[29] "Kosovo"                                              

unique(asian$cntry)

 [1] "Japan"                     "Hong Kong"                 "Republic of Korea"        
 [4] "China"                     "Mongolia"                  "Philippines"              
 [7] "Taiwan, Province of China" "Thailand"                  "Indonesia"                
[10] "Singapore"                 "Viet Nam"                  "Cambodia"                 
[13] "Malaysia"                  "Myanmar"                  

unique(wvs$cntry)

 [1] "Algeria"                   "Argentina"                 "Armenia"                  
 [4] "Australia"                 "Azerbaijan"                "Bahrain"                  
 [7] "Belarus"                   "Brazil"                    "Colombia"                 
[10] "Cyprus"                    "Chile"                     "China"                    
[13] "Ecuador"                   "Egypt"                     "Estonia"                  
[16] "Georgia"                   "Germany"                   "Ghana"                    
[19] "Hong Kong"                 "India"                     "Iraq"                     
[22] "Japan"                     "Jordan"                    "Kazakhstan"               
[25] "Kuwait"                    "Kyrgyzstan"                "Lebanon"                  
[28] "Libya"                     "Malaysia"                  "Mexico"                   
[31] "Morocco"                   "Netherlands"               "New Zealand"              
[34] "Nigeria"                   "Pakistan"                  "Palestine, State of"      
[37] "Peru"                      "Philippines"               "Poland"                   
[40] "Qatar"                     "Romania"                   "Russian Federation"       
[43] "Rwanda"                    "Singapore"                 "Slovenia"                 
[46] "Republic of Korea"         "South Africa"              "Spain"                    
[49] "Sweden"                    "Taiwan, Province of China" "Thailand"                 
[52] "Trinidad and Tobago"       "Tunisia"                   "Turkey"                   
[55] "Ukraine"                   "United States of America"  "Uruguay"                  
[58] "Uzbekistan"                "Yemen"                     "Zimbabwe"                 

unique(latino$cntry)

 [1] "Argentina"                         "Bolivia (Plurinational State of)"  "Brazil"                           
 [4] "Colombia"                          "Costa Rica"                        "Chile"                            
 [7] "Ecuador"                           "El Salvador"                       "Spain"                            
[10] "Guatemala"                         "Honduras"                          "Mexico"                           
[13] "Nicaragua"                         "Panama"                            "Paraguay"                         
[16] "Peru"                              "Dominican Republic"                "Uruguay"                          
[19] "Venezuela, Bolivarian Republic of"

unique(americas$cntry)

 [1] "Bahamas"                          "Barbados"                         "Belize"                          
 [4] "Brazil"                           "Colombia"                         "Costa Rica"                      
 [7] "Dominican Republic"               "Ecuador"                          "El Salvador"                     
[10] "Guatemala"                        "Guyana"                           NA                                
[13] "Honduras"                         "Jamaica"                          "Mexico"                          
[16] "Nicaragua"                        "Panama"                           "Paraguay"                        
[19] "Peru"                             "Suriname"                         "Trinidad and Tobago"             
[22] "Uruguay"                          "Bolivia (Plurinational State of)" "Canada"                          

unique(afro$cntry)

 [1] "Algeria"                     "Burundi"                     "Benin"                      
 [4] "Burkina Faso"                "Botswana"                    "Cameroon"                   
 [7] "Côte D'Ivoire"               "Cabo Verde"                  "Egypt"                      
[10] "Ghana"                       "Guinea"                      "Kenya"                      
[13] "Lesotho"                     "Liberia"                     "Madagascar"                 
[16] "Mauritius"                   "Mali"                        "Malawi"                     
[19] "Mozambique"                  "Morocco"                     "Namibia"                    
[22] "Niger"                       "Nigeria"                     "South Africa"               
[25] "Senegal"                     "Sierra Leone"                "Sudan"                      
[28] "Swaziland"                   "United Republic of Tanzania" "Togo"                       
[31] "Tunisia"                     "Uganda"                      "Zambia"                     
[34] "Zimbabwe"                    "Gabon"                       "Sao Tome and Principe"      

merged <- rbind(wvs, latino, afro, americas, asian, ESS)
merged %<>%
  # create dummies
  mutate(
    wvs = ifelse(survey == "wvs", 1, 0),
  filter(cntry != "Libya") %>% # exclude Libya 2014
  filter(cntry != "Mali") %>% # exclude Mali 2012
  filter(cntry != "Yemen") %>% # exclude Yemen 2012
# adding weight
merged %<>%
# select(cntry, year) %>%
# unique %>%
# View
merged

table(merged$wvs)

     0      1 
301009  80618 

table(merged$afro)

     0      1 
280893 100734 

table(merged$latino)

     0      1 
338714  42913 

table(merged$americas)

     0      1 
311125  70502 

table(merged$asian)

     0      1 
349440  32187 

table(merged$ESS)

     1 
326954  54673 

SEM Index

merged2 <- merged %>%
  mutate(gov_trust = trust_gov + trust_parliament + 
           trust_police + trust_courts) %>%
  filter(!is.na(gov_trust))
merged3 <- merged %>%
  mutate(gov_trust = trust_gov + trust_parliament + 
           trust_police + trust_courts) %>%
  filter(is.na(gov_trust))
svy.df <- survey::svydesign(id= ~1,
                              weights= ~weight,
                              data= merged) 
model <- '# measurement model 1
gov_trust2 =~ 1*trust_gov + trust_parliament + 
trust_police + trust_courts
trust_gov ~~ trust_parliament
'
merged <- merged %>%
  mutate_at(vars(trust_gov, trust_parliament,
                 trust_police, trust_courts), as.numeric)
# cor(na.omit(data.frame(merged$trust_gov,
#               merged$trust_police,
#               merged$trust_courts,
#               merged$trust_parliament,
#               merged$demtoday)))
lavaan_model1<-cfa(model, meanstructure = T, 
                   data = as.data.frame(merged),
                   estimator= "MLM")
fit_a1<-lavaan.survey(lavaan_model1, 
            estimator= "MLM", survey.design=svy.df)
summary(fit_a1, standardized=TRUE,fit.measures = TRUE, rsq = T)

lavaan (0.5-23.1097) converged normally after  38 iterations

  Number of observations                        339509

  Estimator                                         ML      Robust
  Minimum Function Test Statistic                4.858       2.577
  Degrees of freedom                                 1           1
  P-value (Chi-square)                           0.028       0.108
  Scaling correction factor                                  1.885
    for the Satorra-Bentler correction

Model test baseline model:

  Minimum Function Test Statistic           503887.369  334369.533
  Degrees of freedom                                 6           6
  P-value                                        0.000       0.000

User model versus baseline model:

  Comparative Fit Index (CFI)                    1.000       1.000
  Tucker-Lewis Index (TLI)                       1.000       1.000

  Robust Comparative Fit Index (CFI)                         1.000
  Robust Tucker-Lewis Index (TLI)                            1.000

Loglikelihood and Information Criteria:

  Loglikelihood user model (H0)             -159340.600  -159340.600
  Loglikelihood unrestricted model (H1)     -159338.171  -159338.171

  Number of free parameters                         13          13
  Akaike (AIC)                              318707.201  318707.201
  Bayesian (BIC)                            318846.759  318846.759
  Sample-size adjusted Bayesian (BIC)       318805.445  318805.445

Root Mean Square Error of Approximation:

  RMSEA                                          0.003       0.002
  90 Percent Confidence Interval          0.001  0.007       0.000  0.005
  P-value RMSEA <= 0.05                          1.000       1.000

  Robust RMSEA                                               0.003
  90 Percent Confidence Interval                             0.000  0.008

Standardized Root Mean Square Residual:

  SRMR                                           0.000       0.000

Parameter Estimates:

  Information                                 Expected
  Standard Errors                           Robust.sem

Latent Variables:
                   Estimate  Std.Err  z-value  P(>|z|)   Std.lv  Std.all
  gov_trust2 =~                                                         
    trust_gov         1.000                               0.208    0.613
    trust_parlimnt    1.015    0.003  330.156    0.000    0.211    0.653
    trust_police      1.099    0.004  253.511    0.000    0.228    0.700
    trust_courts      1.315    0.005  247.330    0.000    0.273    0.847

Covariances:
                   Estimate  Std.Err  z-value  P(>|z|)   Std.lv  Std.all
 .trust_gov ~~                                                          
   .trust_parlimnt    0.029    0.000  123.012    0.000    0.029    0.438

Intercepts:
                   Estimate  Std.Err  z-value  P(>|z|)   Std.lv  Std.all
   .trust_gov         0.484    0.001  715.884    0.000    0.484    1.428
   .trust_parlimnt    0.456    0.001  703.812    0.000    0.456    1.414
   .trust_police      0.536    0.001  822.959    0.000    0.536    1.644
   .trust_courts      0.515    0.001  796.359    0.000    0.515    1.595
    gov_trust2        0.000                               0.000    0.000

Variances:
                   Estimate  Std.Err  z-value  P(>|z|)   Std.lv  Std.all
   .trust_gov         0.072    0.000  259.086    0.000    0.072    0.624
   .trust_parlimnt    0.060    0.000  226.846    0.000    0.060    0.573
   .trust_police      0.054    0.000  218.146    0.000    0.054    0.510
   .trust_courts      0.029    0.000  107.510    0.000    0.029    0.282
    gov_trust2        0.043    0.000  148.215    0.000    1.000    1.000

R-Square:
                   Estimate
    trust_gov         0.376
    trust_parlimnt    0.427
    trust_police      0.490
    trust_courts      0.718

merged4<-cbind(merged2, predict(fit_a1, newdata = merged2))
merged4$gov_trust2<-range01(merged4$gov_trust2)
# head(merged4)
merged<-plyr::rbind.fill(merged3,merged4)
merged$gov_trust<-merged$gov_trust2
head(merged)

Some Recoding

table(merged$cntry,merged$year)

                                                      
                                                       1582 1583 2000 2010 2011 2012 2013 2014 2015 2077
  Albania                                                 0    0    0    0    0  615  586    0    0    0
  Algeria                                                 0    0    0    0    0    0 2404    0 1200    0
  Argentina                                               0    0    0    0    0    0 2230    0 1200    0
  Armenia                                                 0    0    0    0 1100    0    0    0    0    0
  Australia                                               0    0    0    0    0 1477    0    0    0    0
  Azerbaijan                                              0    0    0    0 1002    0    0    0    0    0
  Bahamas                                                 0    0    0    0    0    0    0 3429    0    0
  Bahrain                                                 0    0    0    0    0    0    0 1200    0    0
  Barbados                                                0    0    0    0    0    0    0 3828    0    0
  Belarus                                                 0    0    0    0 1535    0    0    0    0    0
  Belgium                                                 0    0    0    0    0 1869    0    0    0    0
  Belize                                                  0    0    0    0    0 1512    0 1533    0    0
  Benin                                                   0    0    0    0 1200    0    0 1200    0    0
  Bolivia (Plurinational State of)                        0    0    0    0    0 3029 1200    0 1200    0
  Botswana                                                0    0    0    0    0 1200    0 1200    0    0
  Brazil                                                  0    0    0    0    0 1499 1204 2986 1250    0
  Bulgaria                                                0    0    0    0    0    0 2260    0    0    0
  Burkina Faso                                            0    0    0    0    0 1200    0    0 1200    0
  Burundi                                                 0    0    0    0    0 1200    0 1200    0    0
  Cabo Verde                                              0    0    0    0 1208    0    0 1200    0    0
  Cambodia                                                0    0    0    0    0 1200    0    0 2400    0
  Cameroon                                                0    0    0    0    0    0 1200    0 1182    0
  Canada                                                  0    0    0 1500    0    0    0    0    0    0
  Chile                                                   0    0    0    0 1000    0 1200    0 1200    0
  China                                                   0    3    1    0 3408 2360    0    0    0    1
  Colombia                                                0    0    0    0    0 3024 1200 1496 1200    0
  Costa Rica                                              0    0    0    0    0 1498 1000 1537 1000    0
  Côte D'Ivoire                                           0    0    0    0    0    0 1200 1199    0    0
  Cyprus                                                  0    0    0    0 1000 1089   27    0    0    0
  Czech Republic                                          0    0    0    0    0    0 2009    0    0    0
  Denmark                                                 0    0    0    0    0    0 1650    0    0    0
  Dominican Republic                                      0    0    0    0    0 1512 1000 1520 1000    0
  Ecuador                                                 0    0    0    0    0 1500 2402    0 1200    0
  El Salvador                                             0    0    0    0    0 1497 1000 1512 1000    0
  Estonia                                                 0    0    0    0 1533 2279  101    0    0    0
  Finland                                                 0    0    0    0    0 1884  313    0    0    0
  France                                                  0    0    0    0    0    0 1968    0    0    0
  Gabon                                                   0    0    0    0    0    0    0    0 1198    0
  Georgia                                                 0    0    0    0    0    0    0 1202    0    0
  Germany                                                 0    0    0    0    0 2753 2251    0    0    0
  Ghana                                                   0    0    0    0    0 3952    0 2400    0    0
  Guatemala                                               0    0    0    0    0 1509 1000 1506 1000    0
  Guinea                                                  0    0    0    0    0    0 1200    0 1200    0
  Guyana                                                  0    0    0    0    0 1529    0 1557    0    0
  Honduras                                                0    0    0    0    0 1728 1000 1561 1000    0
  Hong Kong                                               0    0    0    0    0 1207 1000    0    0    0
  Hungary                                                 0    0    0    0    0 1895  119    0    0    0
  Iceland                                                 0    0    0    0    0  601  151    0    0    0
  India                                                   0    0    0    0    0    0    0 1581    0    0
  Indonesia                                               0    0    0    0 1550    0    0    0    0    0
  Iraq                                                    0    0    0    0    0 1200    0    0    0    0
  Ireland                                                 0    0    0    0    0  995 1633    0    0    0
  Israel                                                  0    0    0    0    0 2229  279    0    0    0
  Italy                                                   0    0    0    0    0    0  960    0    0    0
  Jamaica                                                 0    0    0    0    0 1500    0 1503    0    0
  Japan                                                   0    0    0 2443 1880    0    0    0    0    0
  Jordan                                                  0    0    0    0    0    0    0 1200    0    0
  Kazakhstan                                              0    0    0    0 1500    0    0    0    0    0
  Kenya                                                   0    0    0    0 2399    0    0 2397    0    0
  Kosovo                                                  0    0    0    0    0    0 1295    0    0    0
  Kuwait                                                  0    0    0    0    0    0    0 1303    0    0
  Kyrgyzstan                                              0    0    0    0 1500    0    0    0    0    0
  Lebanon                                                 0    0    0    0    0    0 1200    0    0    0
  Lesotho                                                 0    0    0    0    0 1197    0 1200    0    0
  Liberia                                                 0    0    0    0    0 1199    0    0 1199    0
  Lithuania                                               0    0    0    0    0    0 2109    0    0    0
  Madagascar                                              0    0    0    0    0    0 1200 1015  185    0
  Malawi                                                  0    0    0    0    0 2407    0 2400    0    0
  Malaysia                                                0    0    0    0 1214 1300    0 1207    0    0
  Mauritius                                               0    0    0    0    0 1200    0 1200    0    0
  Mexico                                                  0    0    0    0    0 3560 1200 1535 1200    0
  Mongolia                                                0    0    0 1210    0    0    0 1228    0    0
  Morocco                                                 0    0    0    0 1200    0 1196    0 1200    0
  Mozambique                                              0    0    0    0    0 2400    0    0 2400    0
  Myanmar                                                 0    0    0    0    0    0    0    0 1620    0
  Namibia                                                 0    0    0    0    0 1200    0 1200    0    0
  Netherlands                                             0    0    0    0    0 3381  366    0    0    0
  New Zealand                                             0    0    0    0  841    0    0    0    0    0
  Nicaragua                                               0    0    0    0    0 1686 1000 1546 1000    0
  Niger                                                   0    0    0    0    0    0 1199    0 1200    0
  Nigeria                                                 0    0    0    0 1759 2364   36 2319   81    0
  Norway                                                  0    0    0    0    0 1446  178    0    0    0
  Pakistan                                                0    0    0    0    0 1200    0    0    0    0
  Panama                                                  0    0    0    0    0 1620 1000 1508 1000    0
  Paraguay                                                0    0    0    0    0 1510 1200 1503 1200    0
  Peru                                                    0    0    0    0    0 2710 1200 1500 1200    0
  Philippines                                             0    0    0 1200    0 1200    0 1200    0    0
  Poland                                                  0    0    0    0    0 2851   13    0    0    0
  Portugal                                                0    0    0    0    0  395 1756    0    0    0
  Qatar                                                   0    0    0 1060    0    0    0    0    0    0
  Republic of Korea                                       0    0    0 1200 1207    0    0    0 1200    0
  Romania                                                 0    0    0    0    0 1503    0    0    0    0
  Russian Federation                                      0    0    0    0 2500 2484    0    0    0    0
  Rwanda                                                  0    0    0    0    0 1527    0    0    0    0
  Sao Tome and Principe                                   0    0    0    0    0    0    0    0 1196    0
  Senegal                                                 0    0    0    0    0    0 1200 1200    0    0
  Sierra Leone                                            0    0    0    0    0 1190    0    0 1191    0
  Singapore                                            1000    0    0    0    0 1972    0  993   46    0
  Slovakia                                                0    0    0    0    0 1415  432    0    0    0
  Slovenia                                                0    0    0    0 1069 1257    0    0    0    0
 [ reached getOption("max.print") -- omitted 24 rows ]

table(subset(merged,merged$cntry=="China")$survey,
      subset(merged,merged$cntry=="China")$year)

       
        1583 2000 2011 2012 2077
  asian    3    1 3408   60    1
  wvs      0    0    0 2300    0

merged$year[merged$cntry=="China" & merged$year == 1583] <- 2011
merged$year[merged$cntry=="China" & merged$year == 2000] <- 2011
merged$year[merged$cntry=="China" & merged$year == 2077] <- 2011
merged$year[merged$cntry=="China" & merged$year == 2012] <- 2011
table(subset(merged,merged$cntry=="Singapore")$survey,
      subset(merged,merged$cntry=="Singapore")$year)

       
        1582 2012 2014 2015
  asian 1000    0  993   46
  wvs      0 1972    0    0

merged$year[merged$cntry=="Singapore" & merged$year == 1582] <- 2011
hist(merged$gov_trust)

Level 2 Data

V-Dem

To Do - Regions

  mutate(regions = vdems_sub %>% 
           dcast(country_name ~ year, 
                 value.var=c("e_regionpol")) %>%
           select('2000') %>% 
           mutate(regions = fct_recode(as.factor(`2000`),
                                "E. Europe and C. Asia (post-Communist)" = "1",
                                "Latin America & Carribean" = "2",
                                "MENA" = "3",
                                "Sub-Saharan Africa" = "4",
                                "W. Europe and N. America" = "5",
                                "South & East Asia & Pacific" = "6",
                                "South & East Asia & Pacific" = "7",
                                "South & East Asia & Pacific" = "8",
                                "South & East Asia & Pacific" = "9",
                                "Latin America & Carribean" = "10")  %>%
                                as_factor))  %>%
           select(regions)

Error in as_data_frame(data) : 
  argument ".data" is missing, with no default

QoG

load(qog_url)
qog10 <- qog %>% 
  filter(year %in% 2000:2010) %>% 
  mutate(cntry = countrycode(ccodecow, "cown","country.name.en"))
qog10 <- qog %>% 
  filter(year %in% 2000:2010) %>% 
  mutate(cntry = countrycode(ccodecow, "cown","country.name.en")) %>% 
  group_by(cntry) %>%
  tally() %>% 
  mutate(ethnic10 = qog10 %>%
           dcast(cntry ~ year, 
                 value.var=c("al_ethnic"), 
          fun.aggregate = mean) %>%
           select(`2000`:`2010`) %>%
           rowMeans) %>% 
  select(-n)
#  mutate(al_ethnic = as.numeric(al_ethnic)) %>% 
qog10

Merging Time

Level 2

level2 <- merge(x=qog10, y=vdem, by="cntry")
level2

Ind + Country

combined <- merge(x=merged, y=level2, by="cntry") %>% 
              mutate(cntryears = paste(cntry, year))
#combined$cntryears <- paste(combined$cntry,combined$year)
vdem2 <- vdems_start %>%
  filter(year %in% 2010:2015) %>% 
  mutate(cntry = countrycode(country_name,"country.name.en","country.name.en")) #%>% 

Some values were not matched unambiguously: Democratic Republic of Vietnam

 # select(cntry, country_name)
vdem2$cntry[996] <- "Viet Nam"
vdem2$cntry[997] <- "Viet Nam"
vdem2$cntry[998] <- "Viet Nam"
vdem2$cntry[999] <- "Viet Nam"
vdem2$cntry[1000] <- "Viet Nam"
vdem2$cntry[1001] <- "Viet Nam"
combined <- vdem2 %>% 
  mutate(cntryears = paste(cntry, year)) %>% 
  mutate(discuss_unsel = v2xcl_disc) %>% 
  select(cntryears, discuss_unsel) %>% 
  merge(combined, by = "cntryears") %>% 
                  plyr::ddply(~cntry,
                        summarise, 
                        discuss = mean(discuss_unsel, na.rm=T)) %>% 
  merge(combined, by = "cntry")
combined

save(combined,file="combined.Rdata")
save(level2,file="level2.Rdata")

Weighting

Macro Level

macro  <- combined %>% 
                mutate(gov_trust = range01(gov_trust)*100) %>% 
                mutate(demtoday = range01(demtoday)*100) %>% 
                plyr::ddply(~cntry,
                     summarise,
                     mean_gov = mean(gov_trust, na.rm=T),
                     mean_dem = mean(demtoday, na.rm=T),
                     discuss = mean(discuss, na.rm=T)) %>% 
#                     polity10 = mean(polity10, na.rm=T),
#                     polity_demdummy = mean(polity_demdummy, na.rm=T)) %>% 
                mutate(discuss_round = round(discuss*4)) %>% 
                mutate(mean_gov_low = case_when(
                      discuss_round == 2 ~ mean_gov * .9,
                      discuss_round == 1 ~ mean_gov * .85,
                      discuss_round %in% c(3,4) ~ mean_gov)) %>% 
                mutate(mean_gov_high = case_when(
                      discuss_round == 2 ~ mean_gov * .8,
                      discuss_round == 1 ~ mean_gov * .75,
                      discuss_round %in% c(3,4) ~ mean_gov)) %>% 
                merge(level2, by = "cntry") %>% 
                mutate_at(vars(common10, reason10, consult10, 
                 countr10, engage10, engage10, delib10), 
                                          range01)
macro_dem <- macro %>% 
                      filter(polity_demdummy == 1)
macro_aut <- macro %>% 
                      filter(polity_demdummy == 0)
# table_stuff2<-subset(table_stuff,
#                      !is.na(table_stuff$regime) &
#                        table_stuff$cntry!="Qatar" &
#                       table_stuff$cntry!="Uzbekistan")
save(macro, file="macro.Rdata")
save(macro_dem, file="macro_dem.Rdata")
save(macro_aut, file="macro_aut.Rdata")

Individual Level

Crap

compare_cntry<-data.frame(table(merged$cntry,merged$year))
compare_cntry<-tidyr::spread(compare_cntry,Var2,Freq)
compare_cntry[compare_cntry==0]<-100000
#compare_cntry<-na.omit(compare_cntry)
indie<-as.numeric(apply(compare_cntry[,-1],1,sum))
compare_cntry$double<-indie<900000
compare_cntry[compare_cntry==100000]<-0
compare_cntry2 <- subset(compare_cntry,compare_cntry$double==TRUE)

compare_cntry3 <- subset(merged,merged$cntry %in% compare_cntry2$Var1)

y1<-subset(compare_cntry3,compare_cntry3$cntry=="Belize" &
                      compare_cntry3$year==2012)$gov_trust

y2<-subset(compare_cntry3,compare_cntry3$cntry=="Belize" &
         compare_cntry3$year==2014)$gov_trust

t.test(y1,y2)

y1<-subset(compare_cntry3,compare_cntry3$cntry=="Bolivia (Plurinational State of)" &
             compare_cntry3$year==2012)$gov_trust

y2<-subset(compare_cntry3,compare_cntry3$cntry=="Bolivia (Plurinational State of)" &
             compare_cntry3$year==2013)$gov_trust

t.test(y1,y2)

y1<-subset(compare_cntry3,compare_cntry3$cntry=="South Africa" &
             compare_cntry3$year==2011)$gov_trust

y2<-subset(compare_cntry3,compare_cntry3$cntry=="South Africa" &
             compare_cntry3$year==2013)$gov_trust

t.test(y1,y2)

       
subset(merged,merged$year==2012)

library(dplyr)
compare_cntry4 <- compare_cntry3 %>%
  group_by(cntry,year) %>%
  summarise_all(funs(mean(., na.rm=TRUE)))

compare_cntry4$cntryear<-paste(compare_cntry4$cntry,compare_cntry4$year)
  
as.data.frame(compare_cntry4[,c(17,8)])
  
?ddply
head(afro)

afrocntry<-unique(afro$cntry)
latinocntry<-unique(latino2013$cntry)
arabcntry<-unique(arab3$cntry)
wvscntry<-unique(wvs$cntry)

cntry_table<- data.frame(as.character(wvscntry),
                         c(as.character(arabcntry),rep("-",48)),
                         c(as.character(latinocntry),rep("-",41)),
                         c(as.character(afrocntry),rep("-",24)))

colnames(cntry_table) <- c("wvs","arab","latino","afro")

arrange(cntry_table, wvs, afro)



table(combined$politcat.x)
mplusdata <- combined %>% dplyr::select(cntry, delib10, demtoday, 
                                        trust_gov, trust_parliament, 
                                        trust_police,trust_courts,weight)
mplusdata <- na.omit(mplusdata)
mplusdata$cntry <- as.numeric(mplusdata$cntry)
write_csv(mplusdata, path = "mplusdata.csv", col_names = F)

mplusdata2 <- combined %>% dplyr::select(cntry, delib10, demtoday, 
                                        gov_trust,weight)
mplusdata2 <- na.omit(mplusdata2)
mplusdata2$cntry <- as.numeric(mplusdata2$cntry)
write_csv(mplusdata2, path = "mplusdat2a.csv", col_names = F)

mplusdata2_dem <- combined_dem %>% dplyr::select(cntry, delib10, demtoday, 
                                         gov_trust,weight)
mplusdata2_dem <- na.omit(mplusdata2_dem)
mplusdata2_dem$cntry <- as.numeric(mplusdata2_dem$cntry)
write_csv(mplusdata2_dem, path = "mplusdat2_dema.csv", col_names = F)

mplusdata2_aut <- combined_aut %>% dplyr::select(cntry, delib10, demtoday, 
                                         gov_trust,weight)
mplusdata2_aut <- na.omit(mplusdata2_aut)
mplusdata2_aut$cntry <- as.numeric(mplusdata2_aut$cntry)
write_csv(mplusdata2_aut, path = "mplusdat2_auta.csv", col_names = F)

combined <- merge(combined, physi2_s, by = "cntry")

combined_dem <- subset(combined,combined$polity_demdummy==1)

mplusdata_dem <- combined_dem %>% dplyr::select(cntry, delib10, demtoday, 
                                        trust_gov, trust_parliament, 
                                        trust_police,trust_courts,weight)
mplusdata_dem <- na.omit(mplusdata_dem)
mplusdata_dem$cntry <- as.numeric(mplusdata_dem$cntry)
write_csv(mplusdata_dem, path = "mplusdata_dem.csv", col_names = F)


combined_aut <- subset(combined,combined$polity_demdummy==0)

mplusdata_aut <- combined_aut %>% dplyr::select(cntry, delib10, demtoday, 
                                                trust_gov, trust_parliament, 
                                                trust_police,trust_courts,weight)
mplusdata_aut <- na.omit(mplusdata_aut)
mplusdata_aut$cntry <- as.numeric(mplusdata_aut$cntry)
write_csv(mplusdata_aut, path = "mplusdata_aut.csv", col_names = F)


#data_wids <- dcast(merged, cntry~year, 
#                    value.var=c("year"))
#data_wids2 <- as.data.frame(lapply(data_wids[,-1],function(n) 0<n))
#data_wids3 <- as.data.frame(apply(data_wids2,2,as.numeric))
#data_wids3 <- cbind(data_wids[,1],data_wids3)
#names(data_wids3)[1]<-"cntry"
#table_stuff <- merge(data_wids3 ,table_stuff, by="cntry")

#table_stuff$polity10[table_stuff$cntry=="Tunisia"] <- 5.32382
#table_stuff2$polity10[table_stuff2$cntry=="Tunisia"] <- 5.32382

head(table_stuff)
cor(na.omit(data.frame(table_stuff$legit,table_stuff$legit2,table_stuff$legit3,
                       table_stuff$mean_gov)))

table_stuff$gni <- table_stuff$gni_c

table_stuff$gni_c[table_stuff$gni <= 1025] <- "low"
table_stuff$gni_c[table_stuff$gni > 1026 & table_stuff$gni <= 4035] <- "lower-middle"
table_stuff$gni_c[table_stuff$gni > 4036 & table_stuff$gni <= 12475] <- "upper-middle"
table_stuff$gni_c[table_stuff$gni > 12475] <- "high"

table_stuff$gni_c2 <- table_stuff$gni_c

table_stuff$gni_c2[table_stuff$gni_c == "lower-middle"] <- "low"
table_stuff$gni_c2[table_stuff$gni_c == "upper-middle"] <- "high"

table(table_stuff$gni_c)
table(table_stuff$gni_c2)

The cut-off points are HDI of less than 0.550
for low human development, 0.550-0.699 for medium human
development, 0.700-0.799 for high human development and
0.800 or greater for very high human development.

#table_stuff$hdi_c <- table_stuff$hdi

#table_stuff$hdi_c[table_stuff$hdi < 0.550] <- "low"
#table_stuff$hdi_c[table_stuff$hdi >= 0.550 & table_stuff$hdi <= 0.699] <- "medium"
#table_stuff$hdi_c[table_stuff$hdi >= 0.700 & table_stuff$hdi <= 0.899] <- "high"
#table_stuff$hdi_c[table_stuff$hdi >= 0.90] <- "very high"

#table(table_stuff$hdi_c)



table(round(table_stuff$terror))

table_stuff$mean_gov2 <- table_stuff$mean_gov
table_stuff$mean_gov2[is.na(table_stuff$mean_gov2)]<-999

table_stuff$mean_gov3 <- table_stuff$mean_gov
table_stuff$mean_gov3[is.na(table_stuff$mean_gov3)]<-999

table_stuff$mean_gov4 <- table_stuff$mean_gov
table_stuff$mean_gov4[is.na(table_stuff$mean_gov4)]<-999

table_stuff$mean_gov5 <- table_stuff$mean_gov
table_stuff$mean_gov5[is.na(table_stuff$mean_gov5)]<-999

table_stuff$mean_gov6 <- table_stuff$mean_gov
table_stuff$mean_gov6[is.na(table_stuff$mean_gov6)]<-999

table_stuff$mean_gov7 <- table_stuff$mean_gov
table_stuff$mean_gov7[is.na(table_stuff$mean_gov7)]<-999

table_stuff$mean_gov8 <- table_stuff$mean_gov
table_stuff$mean_gov8[is.na(table_stuff$mean_gov8)]<-999

table_stuff$mean_gov9 <- table_stuff$mean_gov
table_stuff$mean_gov9[is.na(table_stuff$mean_gov9)]<-999

table_stuff$physviol2 <- table_stuff$physviol
table_stuff$physviol2[is.na(table_stuff$physviol2)] <- 999

table_stuff$terror2 <- round(table_stuff$terror)
table_stuff$terror2[is.nan(table_stuff$terror2)] <- 999

table_stuff$discuss2 <- round(table_stuff$discuss*4)
table_stuff$discuss2[is.nan(table_stuff$discuss2)] <- 999



table(table_stuff$physviol)
table_stuff$mean_gov2[table_stuff$physviol2<=0.5 & table_stuff$physviol2>0.4] <- table_stuff$mean_gov2[table_stuff$physviol2<=0.5 & table_stuff$physviol2>0.4]-5
table_stuff$mean_gov2[table_stuff$physviol2<=0.4 & table_stuff$physviol2>0.3] <- table_stuff$mean_gov2[table_stuff$physviol2<=0.4 & table_stuff$physviol2>0.3]-10
table_stuff$mean_gov2[table_stuff$physviol2<=0.3 & table_stuff$physviol2>0.2] <- table_stuff$mean_gov2[table_stuff$physviol2<=0.3 & table_stuff$physviol2>0.2]-15
table_stuff$mean_gov2[table_stuff$physviol2<=0.2 & table_stuff$physviol2>0.1] <- table_stuff$mean_gov2[table_stuff$physviol2<=0.2 & table_stuff$physviol2>0.1]-20
table_stuff$mean_gov2[table_stuff$physviol2<=0.1 & table_stuff$physviol2>=0]  <- table_stuff$mean_gov2[table_stuff$physviol2<=0.1 & table_stuff$physviol2>=0]  -25

table_stuff$mean_gov2[table_stuff$mean_gov2>100] <- NA
table(table_stuff$mean_gov2)

table_stuff$mean_gov3[table_stuff$physviol2<=0.5 & table_stuff$physviol2>0.4] <- table_stuff$mean_gov3[table_stuff$physviol2<=0.5 & table_stuff$physviol2>0.4]-8
table_stuff$mean_gov3[table_stuff$physviol2<=0.4 & table_stuff$physviol2>0.3] <- table_stuff$mean_gov3[table_stuff$physviol2<=0.4 & table_stuff$physviol2>0.3]-16
table_stuff$mean_gov3[table_stuff$physviol2<=0.3 & table_stuff$physviol2>0.2] <- table_stuff$mean_gov3[table_stuff$physviol2<=0.3 & table_stuff$physviol2>0.2]-24
table_stuff$mean_gov3[table_stuff$physviol2<=0.2 & table_stuff$physviol2>0.1] <- table_stuff$mean_gov3[table_stuff$physviol2<=0.2 & table_stuff$physviol2>0.1] -32
table_stuff$mean_gov3[table_stuff$physviol2<=0.1 & table_stuff$physviol2>=0] <-  table_stuff$mean_gov3[table_stuff$physviol2<=0.1 & table_stuff$physviol2>=0]  -30

table_stuff$mean_gov3[table_stuff$mean_gov3>100] <- NA
table(table_stuff$mean_gov3)

table_stuff$mean_gov4[table_stuff$terror2==5] <- table_stuff$mean_gov4[table_stuff$terror2==5]-5
table_stuff$mean_gov4[table_stuff$terror2==4] <- table_stuff$mean_gov4[table_stuff$terror2==4]-10
table_stuff$mean_gov4[table_stuff$terror2==3] <- table_stuff$mean_gov4[table_stuff$terror2==3]-15

table_stuff$mean_gov4[table_stuff$mean_gov4>100] <- NA
table(table_stuff$mean_gov4)

table_stuff$mean_gov5[table_stuff$terror2==5] <- table_stuff$mean_gov5[table_stuff$terror2==5]-8
table_stuff$mean_gov5[table_stuff$terror2==4] <- table_stuff$mean_gov5[table_stuff$terror2==4]-16
table_stuff$mean_gov5[table_stuff$terror2==3] <- table_stuff$mean_gov5[table_stuff$terror2==3]-24

table_stuff$mean_gov5[table_stuff$mean_gov5>100] <- NA
table(table_stuff$mean_gov5)

table_stuff$mean_gov6[table_stuff$discuss2==2] <- table_stuff$mean_gov6[table_stuff$discuss2==2] -5
table_stuff$mean_gov6[table_stuff$discuss2==1] <- table_stuff$mean_gov6[table_stuff$discuss2==1] -10

table_stuff$mean_gov6[table_stuff$mean_gov6>100] <- NA
table(table_stuff$mean_gov6)

table_stuff$mean_gov7[table_stuff$discuss2==2] <- table_stuff$mean_gov7[table_stuff$discuss2==2] -10
table_stuff$mean_gov7[table_stuff$discuss2==1] <- table_stuff$mean_gov7[table_stuff$discuss2==1] -20

table_stuff$mean_gov7[table_stuff$mean_gov7>100] <- NA
table(table_stuff$mean_gov7)


load(qog_url)

qog10 <- subset(qog,qog$year==2000 |
                  qog$year==2001 |  
                  qog$year==2002 | 
                  qog$year==2003 | 
                  qog$year==2004 | 
                  qog$year==2005 | 
                  qog$year==2006 | 
                  qog$year==2007 | 
                  qog$year==2008 | 
                  qog$year==2009 |
                  qog$year==2010)

library(countrycode)
qog10$cntry<-countrycode(qog10$ccodecow, "cown","country.name.en")
qog10$al_ethnic<-as.numeric(qog10$al_ethnic)
#tidyr::gather(qog10,c("cntry","year"),"al_ethnic")

qog10a <- qog10 %>% dplyr::select(cntry,year,al_ethnic) %>%
  as.data.frame()
data_wide17 <- reshape(data = qog10a,
                       idvar = "cntry",
                       v.names = "al_ethnic",
                       timevar = "year",
                       direction = "wide")

#qog10hdi <- qog10 %>% dplyr::select(cntry,year,undp_hdi) %>%
#  as.data.frame()
#data_wide_hdi <- hdi
  #reshape(data = qog10hdi,
                      # idvar = "cntry",
                      # v.names = "undp_hdi",
                      # timevar = "year",
                      # direction = "wide")



table(qog$al_ethnic,qog$year)

qog14 <- subset(qog,qog$year==2014)
qog14$cntry<-countrycode(qog14$ccodecow, "cown","country.name.en")
qog14 <- qog14 %>% dplyr::select(cntry,year,cspf_legit) %>%
  as.data.frame()
data_wide18 <- reshape(data = qog14,
                       idvar = "cntry",
                       v.names = "cspf_legit",
                       timevar = "year",
                       direction = "wide")

qog15 <- subset(qog,qog$year==2015)
qog15$cntry<-countrycode(qog15$ccodecow, "cown","country.name.en")
qog15 <- qog15 %>% dplyr::select(cntry,year,ffp_sl) %>%
  as.data.frame()
data_wide19 <- reshape(data = qog15,
                       idvar = "cntry",
                       v.names = "ffp_sl",
                       timevar = "year",
                       direction = "wide")


qog10$ciri_physint<-as.numeric(qog10$ciri_physint)
qog10a <- qog10 %>% dplyr::select(cntry,year,ciri_physint) %>%
  as.data.frame()
data_wide20 <- reshape(data = qog10a,
                       idvar = "cntry",
                       v.names = "ciri_physint",
                       timevar = "year",
                       direction = "wide")

qog10$gd_ptss <-as.numeric(qog10$gd_ptss)
qog10a <- qog10 %>% dplyr::select(cntry,year,gd_ptss) %>%
  as.data.frame()
data_wide21 <- reshape(data = qog10a,
                       idvar = "cntry",
                       v.names = "gd_ptss",
                       timevar = "year",
                       direction = "wide")

qog14<-subset(qog,qog$year==2014)
qog13<-subset(qog,qog$year==2013)
qog12<-subset(qog,qog$year==2012)
qog11<-subset(qog,qog$year==2011)
qog10<-subset(qog,qog$year==2010)
qog8<-subset(qog,qog$year==2008)
qog7<-subset(qog,qog$year==2007)
qog6<-subset(qog,qog$year==2006)
qog5<-subset(qog,qog$year==2005)
qog4<-subset(qog,qog$year==2004)
qog3<-subset(qog,qog$year==2003)
qog2<-subset(qog,qog$year==2002)
qog1<-subset(qog,qog$year==2001)
qog0<-subset(qog,qog$year==2000)



table(is.na(qog$wel_culture),qog$year)
culreg<- pmax(qog14$wel_culture, qog13$wel_culture, na.rm = TRUE)
culreg<- pmax(culreg, qog12$wel_culture, na.rm = TRUE)
culreg<- pmax(culreg, qog11$wel_culture, na.rm = TRUE)
culreg<- pmax(culreg, qog10$wel_culture, na.rm = TRUE)
culreg<- pmax(culreg, qog8$wel_culture, na.rm = TRUE)
culreg<- pmax(culreg, qog7$wel_culture, na.rm = TRUE)
culreg<- pmax(culreg, qog6$wel_culture, na.rm = TRUE)
culreg<- pmax(culreg, qog5$wel_culture, na.rm = TRUE)
culreg<- pmax(culreg, qog4$wel_culture, na.rm = TRUE)
culreg<- pmax(culreg, qog3$wel_culture, na.rm = TRUE)
culreg<- pmax(culreg, qog2$wel_culture, na.rm = TRUE)
culreg<- pmax(culreg, qog1$wel_culture, na.rm = TRUE)
culreg<- pmax(culreg, qog0$wel_culture, na.rm = TRUE)
culreg<- as.character(sjmisc::to_label(culreg))
culreg<-as.data.frame(cbind(culreg,qog14$ccodecow))
oreast  <- subset(culreg, culreg$culreg == "Orthodox East")
oreast

#culreg<- pmax(culreg, qog10$wel_culture, na.rm = TRUE)

qog14$ht_region 

culreg$cntry<-countrycode(culreg$V2, "cown","country.name.en")
tabeletto<-merge(table_stuff,culreg,by="cntry")
tabeletto<-as.data.frame(cbind(table_stuff$regions,
                               as.character(table_stuff$cntry),
                               as.character(tabeletto$culreg)))
tabeletto <- tabeletto[order(tabeletto$V1, tabeletto$V3),]
#edit(tabeletto)

culreg<-data.frame(cbind(tabeletto,culreg))
culreg<-culreg[,c(2,4)]
names(culreg)[1]<-c("cntry")

table_stuff3 <- merge(table_stuff,culreg,by="cntry")

table(as.character(tabeletto$V3))

qog100 <- subset(qog,qog$year==2010)
qog100$cntry<-countrycode(sjmisc::to_label(qog100$ccodecow), "cown","country.name.en")
qog100 <- qog100 %>% dplyr::select(cntry,year,ht_regtype1) %>%
  as.data.frame()
qog100$regtype<-sjmisc::to_label(qog100$ht_regtype1)
qog100$year <- NULL
qog100$ht_regtype1 <- NULL
table(qog100$regtype)


ethnic10<-as.numeric(rowMeans(data_wide17[,2:12])) # mean over last 10 years (2000 - 2010)
physint10<-as.numeric(rowMeans(data_wide20[,2:12])) # mean over last 10 years (2000 - 2010)
terror10<-as.numeric(rowMeans(data_wide21[,2:12])) # mean over last 10 years (2000 - 2010)
legit<-as.numeric(data_wide18[,2]) # mean over last 10 years (2000 - 2010)
legit2<-as.numeric(data_wide19[,2]) # mean over last 10 years (2000 - 2010)
qogthingy<-data.frame(data_wide19[,1],ethnic10,legit,legit2,physint10,terror10)
colnames(qogthingy)[1]<-c("cntry")
qogthingy<-merge(x=qogthingy, y=qog100, by="cntry")

#qogthingy<-data.frame(data_wide17[,1],ethnic10)
#colnames(qogthingy)[1]<-c("cntry")
#combined <- merge(x=qogthingy, y=combined, by="cntry")


qog_cs <-read_spss("C:/Users/Favone/Downloads/qog_std_cs_jan17.sav") #loading dataset
qog_cs$cntry<-countrycode(qog_cs$ccodecow, "cown","country.name.en")
qog_cs$legit3<-as.numeric(qog_cs$gov_ixlegitimacyindex)

legit_dat<-data.frame(qog_cs$cntry,qog_cs$legit3)
colnames(legit_dat)<-c("cntry","legit3")

aggrdelib <- merge(x=legit_dat, y=aggrdelib, by="cntry")

aggrdelib$legit3 <- range01(aggrdelib$legit3)
cor(na.omit(aggrdelib[,c(4,5,7,13)]))
cor(na.omit(aggrdelib[,c(4,5,2,6:13)]))

aggrdelib$legit <- 1-range01(aggrdelib$legit)
aggrdelib$legit2 <- 1-range01(aggrdelib$legit2)
aggrdelib$asia <- aggrdelib$e.asia + aggrdelib$s.e.asia + aggrdelib$s.asia + aggrdelib$pacific

SFI <-read_spss("C:/Users/Favone/Downloads/SFIv2016.sav") #loading dataset
SFI <- subset(SFI,SFI$year==2015)
SFI$cntry <-countrycode(SFI$country, "country.name.en","country.name.en") 
SFI$cntry[79] <- "North Korea"
SFI$cntry <-countrycode(SFI$cntry, "country.name.en","country.name.en") 
SFI$legitimacy <- SFI$legit
SFI$legit <- NULL


aggrdelib <- merge(x=SFI, y=aggrdelib, by="cntry")

hdi <- read_csv("hdi.csv")
hdi$cntry<-countrycode(hdi$Country, "country.name.en","country.name.en")
hdi$'1990'<- NULL ; hdi$'1991'<- NULL ; hdi$'1992'<- NULL ; hdi$'1993'<- NULL
hdi$'1994'<- NULL; hdi$'1995'<- NULL; hdi$'1996'<- NULL; hdi$'1997'<- NULL
hdi$'1998'<- NULL ; hdi$'1999'<- NULL ; hdi$'2011'<- NULL ; hdi$'2012'<- NULL
hdi$'2013'<- NULL; hdi$'2014'<- NULL; hdi$'2015'<- NULL;hdi$`HDI Rank (2015)`<- NULL
hdi$Country<- NULL
hdi10<-as.numeric(rowMeans(hdi[,1:11])) 
hdat<-data.frame(hdi$cntry,hdi10) 
names(hdat)<-c("cntry","hdi10")

aggrdelib <- merge(x=hdat, y=aggrdelib, by="cntry")
#table(aggrdelib$hdi10)
#gc()
#combined <- merge(x=hdat, y=combined, by="cntry")


#colnames(aggrdelib)[9]<-"e_p_polity"
#lop<-subset(vdems_start,vdems_start$year==2010)

cor(na.omit(aggrdelib2[,2:17]))
cor(na.omit(data.frame(aggrdelib$polity10,aggrdelib$delib10)))

#hist(vdems$v2dlconslt)
#hist(vdems$v2xcl_disc)
#table(vdems_start$e_boix_regime,vdems_start$year)
#table(vdems_sub$e_p_polity,vdems_sub$year)

##### merging time ####

combined <- merge(x=merged, y=aggrdelib, by="cntry")
table(combined$cntry)

combined <- as.data.frame(combined)
combined$gov_trust <- as.numeric(combined$gov_trust)
combined$age <- as.numeric(combined$age)
combined$income <- as.numeric(combined$income)
combined$educ <- as.numeric(combined$educ)
combined$sex <- as.factor(combined$sex)
combined$authoritarian <- as.numeric(combined$authoritarian)
combined$safety <- as.numeric(combined$safety)
combined$demtoday <- as.numeric(combined$demtoday)
combined$latino <- factor(combined$latino)
combined$afro <- factor(combined$afro)
combined$americas <- factor(combined$americas)
combined$asia <- combined$e.asia + combined$s.e.asia + combined$s.asia + combined$pacific

cor(na.omit(data.frame(combined$gov_trust,combined$income,combined$educ, #Socioeconomic factors
                       combined$delib10, combined$polity10, combined$gdp10, combined$demtoday)))

combined$cntry<-as.factor(combined$cntry)


#combined$polity10 <- combined$polity10*20-10

#combined$regime <- combined$polity10
#combined$regime[combined$polity_autodummy==1] <- "auto"
#combined$regime[combined$polity_anodummy==1] <- "ano"
#combined$regime[combined$polity_demdummy==1] <- "demo"

hist(combined$gov_trust)
qplot(combined$gov_trust)

combined$cntry



#physi_s <- vdems_sub2 %>% dplyr::select(cntryears, franz)

#combined <- merge(combined, physi_s, by = "cntryears")

#physi2_s <- ddply(combined,~cntry,
#                summarise,politcat=mean(franz,na.rm=T))

#combined <- merge(combined, physi2_s, by = "cntry")


vdems_sub2$cntryears <- paste(vdems_sub2$cntry,vdems_sub2$year)

physi <- vdems_sub2 %>% dplyr::select(cntryears, perc)

combined <- merge(combined, physi, by = "cntryears")

physi2 <- ddply(combined,~cntry,
                     summarise,physviol=mean(perc,na.rm=T))

combined <- merge(combined, physi2, by = "cntry")





#physi_22$dis3 <-round(physi_22$dis2)

#unique(physi2_s$cntry)

#1-2.5
#3-5
#5.5 - 7
#physi2_s$politcat2<-8-((physi2_s$politcat) * (7/10))
#11 

#physi2_s$polity_demdummy <- physi2_s$politcat2
#physi2_s$polity_demdummy [physi2_s$politcat2 <= 2.5] <- 1
#physi2_s$polity_demdummy [physi2_s$politcat2 >  2.5] <- 0
#table(physi2_s$polity_demdummy)

#physi2_s$polity_anodummy <- physi2_s$politcat2
#physi2_s$polity_anodummy[physi2_s$politcat2 > 2.5 & physi2_s$politcat2 < 5.5] <- 1
#physi2_s$polity_anodummy[physi2_s$politcat2 <= 2.5 | physi2_s$politcat2 >= 5.5] <- 0
#table(physi2_s$polity_anodummy)

#physi2_s$polity_autodummy <- physi2_s$politcat2
#physi2_s$polity_autodummy[physi2_s$politcat2 >= 5.5] <- 1
#physi2_s$polity_autodummy[physi2_s$politcat2 < 5.5] <- 0
#table(physi2_s$polity_autodummy)

#physi2_s$regime <- physi2_s$politcat
#physi2_s$regime[physi2_s$polity_autodummy==1] <- "auto"
#physi2_s$regime[physi2_s$polity_anodummy==1] <- "ano"
#physi2_s$regime[physi2_s$polity_demdummy==1] <- "demo"

#unique(physi2_s$cntry)

table(physi2_s$regime)

qog2000 <- subset(qog,qog$year==2010 |
                       qog$year==2011 |  
                       qog$year==2012 | 
                       qog$year==2013 | 
                       qog$year==2014 | 
                       qog$year==2015)

table(qog2000$gd_ptsa,qog2000$year)

qog2000$perc2 <- qog2000$gd_ptsa

qog2000$cntry<-countrycode(qog2000$ccodecow, "cown","country.name.en")

qog2000$cntryears <- paste(qog2000$cntry,qog2000$year)

physi2000 <- qog2000 %>% dplyr::select(cntryears, perc2)

combined <- merge(combined, physi2000, by = "cntryears")

physi22000 <- ddply(combined,~cntry,
                summarise,terror=mean(perc2,na.rm=T))

combined <- merge(combined, physi22000, by = "cntry")

#table(qog2000$undp_hdi,qog2000$year)

#physiff <- qog2000 %>% dplyr::select(cntryears, undp_hdi)

#combined <- merge(combined, physiff, by = "cntryears")

#physiff2 <- ddply(combined,~cntry,
#                    summarise,hdi=mean(undp_hdi,na.rm=T))

#combined <- merge(combined, physiff2, by = "cntry")


gni <- read_csv("GNI.csv",  skip = 1)

gni$`2015`<-gsub("ttt","",gni$`2015`)
gni$`2015`<-gsub("ff","",gni$`2015`)
gni$`2015`<-gsub("sss","",gni$`2015`)
gni$`2015`<-gsub("uuu","",gni$`2015`)
gni$`2015`<-gsub("o","",gni$`2015`)
gni$`2015` <- as.numeric(gni$`2015`)

gni$`2014`<-gsub("ttt","",gni$`2014`)
gni$`2014`<-gsub("ff","",gni$`2014`)
gni$`2014`<-gsub("sss","",gni$`2014`)
gni$`2014`<-gsub("uuu","",gni$`2014`)
gni$`2014`<-gsub("o","",gni$`2014`)
gni$`2014` <- as.numeric(gni$`2014`)

gni<-gni[,c(2,23:28)]

gni<-gather(as.data.frame(gni),key = "Country")
names(gni) <- c("cntry","year","gni")

gni$cntry<-countrycode(gni$cntry,"country.name.en","country.name.en")
gni$cntryears <- paste(gni$cntry,gni$year)

physigni <- gni %>% dplyr::select(cntryears, gni)

combined <- merge(combined, physigni, by = "cntryears")

physigni2 <- ddply(combined,~cntry,
                    summarise,gni_c=mean(gni,na.rm=T))

combined <- merge(combined, physigni2, by = "cntry")